Proceedings of the 3rd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2024, May 24–26, 2024, Jinan, China

Research Article

Prediction of Long-term Deposit Customers Using SVM Optimized with Borderline-SMOTE

Download28 downloads
  • @INPROCEEDINGS{10.4108/eai.24-5-2024.2350156,
        author={Yunyi  Gao},
        title={Prediction of Long-term Deposit Customers Using SVM Optimized with Borderline-SMOTE},
        proceedings={Proceedings of the 3rd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2024, May 24--26, 2024, Jinan, China},
        publisher={EAI},
        proceedings_a={MSEA},
        year={2024},
        month={10},
        keywords={economic situation; long-term deposits; capital stability; machine learning},
        doi={10.4108/eai.24-5-2024.2350156}
    }
    
  • Yunyi Gao
    Year: 2024
    Prediction of Long-term Deposit Customers Using SVM Optimized with Borderline-SMOTE
    MSEA
    EAI
    DOI: 10.4108/eai.24-5-2024.2350156
Yunyi Gao1,*
  • 1: Nanjing Agricultural University, Nanjing, China
*Contact email: 2911458297@qq.com

Abstract

As the economic situation and market environments continually evolve, the financial sector faces numerous challenges, one of which is effectively enhancing the capacity to attract long-term deposits. Long-term deposits are crucial for the stability of a bank's capital and are also a critical factor in enabling banks to offer loans at lower costs. This paper aims to identify existing customers who are highly likely to subscribe to long-term deposits by employing machine learning techniques, thereby helping banks to more accurately target their marketing strategies and improve the efficiency of resource utilization.